Extending equation-based congestion control to multicast applications

In this paper we introduce TFMCC, an equation-based multicast congestion control mechanism that extends the TCP-friendly TFRC protocol from the unicast to the multicast domain. The key challenges in the design of TFMCC lie in scalable round-trip time measurements, appropriate feedback suppression, and in ensuring that feedback delays in the control loop do not adversely affect fairness towards competing flows. A major contribution is the feedback mechanism, the key component of end-to-end multicast congestion control schemes. We improve upon the well-known approach of using exponentially weighted random timers by biasing feedback in favor of low-rate receivers while still preventing a response implosion. We evaluate the design using simulation, and demonstrate that TFMCC is both TCP-friendly and scales well to multicast groups with thousands of receivers. We also investigate TFMCC's weaknesses and scaling limits to provide guidance as to application domains for which it is well suited.

[1]  Ernst W. Biersack,et al.  Scalable feedback for large groups , 1999, TNET.

[2]  Jörg Widmer,et al.  Extremum Feedback for Very Large Multicast Groups , 2001, Networked Group Communication.

[3]  Steven McCanne,et al.  A reliable multicast framework for light-weight sessions and application level framing , 1995, SIGCOMM '95.

[4]  Matthew Mathis,et al.  The macroscopic behavior of the TCP congestion avoidance algorithm , 1997, CCRV.

[5]  Michael Mitzenmacher,et al.  FLID-DL: congestion control for layered multicast , 2000, COMM '00.

[6]  Scott O. Bradner,et al.  IETF Criteria for Evaluating Reliable Multicast Transport and Application Protocols , 1998, RFC.

[7]  Injong Rhee,et al.  TEAR: TCP emulation at receivers – flow control for multimedia streaming , 2000 .

[8]  Jon Crowcroft,et al.  TCP-like congestion control for layered multicast data transfer , 1998, Proceedings. IEEE INFOCOM '98, the Conference on Computer Communications. Seventeenth Annual Joint Conference of the IEEE Computer and Communications Societies. Gateway to the 21st Century (Cat. No.98.

[9]  Brian C. Huffman,et al.  Internet Timekeeping Around the Globe , 1997 .

[10]  Satish Kumar,et al.  Improving Simulation for Network Research , 1999 .

[11]  Donald F. Towsley,et al.  The loss path multiplicity problem in multicast congestion control , 1999, IEEE INFOCOM '99. Conference on Computer Communications. Proceedings. Eighteenth Annual Joint Conference of the IEEE Computer and Communications Societies. The Future is Now (Cat. No.99CH36320).

[12]  Mark Handley,et al.  Session directories and scalable Internet multicast address allocation , 1998, SIGCOMM '98.

[13]  S. Gupta,et al.  Order Statistics from the Gamma Distribution , 1960 .

[14]  Mark Handley,et al.  Equation-based congestion control for unicast applications , 2000, SIGCOMM 2000.

[15]  Martin Vetterli,et al.  Receiver-driven layered multicast , 1996, SIGCOMM 1996.

[16]  Jörg Widmer,et al.  On the scaling of feedback algorithms for very large multicast groups , 2001, Comput. Commun..

[17]  Mark Allman,et al.  A web server's view of the transport layer , 2000, CCRV.

[18]  Luigi Rizzo,et al.  pgmcc: a TCP-friendly single-rate multicast , 2000, SIGCOMM.

[19]  Donald F. Towsley,et al.  Modeling TCP Reno performance: a simple model and its empirical validation , 2000, TNET.